Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 19-LLAMASCOPE-RES-32K
    6. 25980
    Prev
    Next
    INDEX
    Explanations

    references to personal information and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idUser
    -0.15
    atus
    -0.14
    ze
    -0.14
    lings
    -0.14
    ivre
    -0.14
     kostenlose
    -0.13
    ural
    -0.13
    ÅĻi
    -0.13
    ATUS
    -0.13
     Yates
    -0.13
    POSITIVE LOGITS
     name
    0.52
     names
    0.47
     Name
    0.37
    åIJįåŃĹ
    0.37
    name
    0.35
     tên
    0.34
    åIJįç§°
    0.33
    .name
    0.33
     Names
    0.33
    -name
    0.33
    Activations Density 0.274%

    No Known Activations